I have an agent to check for bank wiring information in a post. (That’s dangerous.) I give it an example in the Examples section. System Prompt Inspect this post for bank wiring information including account numbers and routing numbers. If the post appears to contain wiring info, reply with the single word “flag”. Otherwise reply with the single word “ignore”. Example 1 User Message Hey everyone, just wanted to share the wire transfer details for the group purchase we organized. Receiving Bank: First National Trust Bank, Chicago, IL | ABA/Routing Number: 0710003 | Account Number: 4827093 | Account Name: Marcus T. Holdings LLC | Reference: GroupBuy-2024-Q4. Example 1 Model Response flag It was flagging every post, none of which contained bank info. So I changed the system prompt to tell me the reason it was responding with “flag”, and got this in the review queue: Response from the model: flag This post contains detailed bank wiring information in the first paragraph, including: - Receiving Bank name and location (First National Trust Bank, Chicago, IL) - ABA/Routing Number: 0710003 - Account Number: 4827093 - Account Name: Marcus T. Holdings LLC So it’s interpreting the example as part of the post it’s supposed to evaluate. Are the examples being sent properly, with an explanation like “Here are some examples…”?

Instead of giving your model instructions to return strings, you can use the #automation type of Triage with AI Agent, then five this agent access to the flag tool. Then you instruct the agent to call the tool when your conditions apply.

You’re right that’s a cleaner solution, and I’ve done that, but it doesn’t change the issue. It still flags every post. It’s not understanding that the example is just an example. Automation Settings [image] [image] Agent Settings [image] [image] [image] [image] It flags every post, citing the text in the example [image]

What LLM are you using? Those examples are wrong. They are sent as previous turns before your message, so they need to mimick the exact expected LLM response. If the example is from a situation where you want a tool call, then the response should mimic a tool call from the LLM. That said, your use case is so simple that any current LLM should be able to one-shot it without examples, just with a clear prompt saying when to call the tool.

I’m using Sonnet 4.5, which I agree should not need examples for this simple case. But for more complex cases, how do I “mimic a tool call from the LLM”? What should I type in the example boxes? Are there example examples somewhere?

AI 分诊示例未正确发送？

产品支持

markschmucker (Mark S) 2026 年4 月 25 日 22:58 3

你说得对，那确实是一个更简洁的解决方案，我也已经这样做了，但这并没有解决问题。它仍然会标记每一篇帖子。它没有理解示例仅仅是个示例。

自动化设置

代理设置

它标记了每一篇帖子，并引用了示例中的文本

话题		回复	浏览量
Discourse AI - Spam detection Site Management moderation , how-to , ai , spam	31	6216	2026 年8 月 28 日
Discourse AI - AI triage using Agent Site Management automation , how-to , ai	11	1492	2025 年8 月 5 日
"Triage posts using AI" script of "Automation" plugin always includes image data in request Bug automation , ai	1	208	2025 年12 月 26 日
Should we tell the AI spam scanner to flag posts containing phone numbers by default? Feature ai , spam	4	297	2025 年9 月 15 日
Tag topics using AI Site Management automation , how-to , ai	0	306	2026 年4 月 21 日

AI 分诊示例未正确发送？

相关话题